Research map / Image generation / Super-resolution
Enhancing the Spatial Resolution of Stereo Images Using a Parallax Prior
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use the stereo parallax prior and jointly trained luminance/chrominance networks instead of the strongest listed single-image baseline | Stereo super-resolution method · Middlebury, ×2 to ×4 | PSNR: 31.62 -> 33.05; 29.30 -> 29.59; 27.23 -> 26.80 | Mixed |
| Use the stereo parallax prior and jointly trained luminance/chrominance networks instead of the strongest listed single-image baseline | Stereo super-resolution method · Tsukuba, ×2 to ×4 | PSNR: 40.50 -> 43.30; 36.70 -> 37.32; 33.40 -> 34.40 | Helped |
| Use the stereo parallax prior and jointly trained luminance/chrominance networks instead of the strongest listed single-image baseline | Stereo super-resolution method · KITTI 2012, ×2 to ×4 | PSNR: 29.48 -> 30.30; 27.24 -> 27.96; 25.44 -> 25.75 | Helped |
| Use the stereo parallax prior and jointly trained luminance/chrominance networks instead of the strongest listed single-image baseline | Stereo super-resolution method · KITTI 2015, ×2 to ×4 | PSNR: 28.60 -> 29.36; 26.37 -> 26.96; 24.50 -> 24.83 | Helped |
| Increase the number of shifted right-view input images (ablation) | Luminance network · Stereo super-resolution training | PSNR | Helped |
| Use 16 luminance-network layers rather than more than 16 (ablation) | Luminance network · Stereo super-resolution training | PSNR | No clear effect |
| Remove the activation function from the last luminance layer (ablation) | Luminance network · Stereo super-resolution training | PSNR | Helped |
| Add a final convolutional layer to semi-residual chrominance learning (ablation) | Chrominance network · Color reconstruction | PSNR | Helped |
Closest papers by meaning
- Learning Parallax Attention for Stereo Image Super-Resolution (CVPR 2019 · similarity 0.90)
- Learned Binocular-Encoding Optics for RGBD Imaging Using Joint Stereo and Focus Cues (CVPR 2025 · similarity 0.86)
- Disparity-Aware Domain Adaptation in Stereo Image Restoration (CVPR 2020 · similarity 0.85)
- Stereoscopic Image Super-Resolution with Stereo Consistent Feature (AAAI 2020 · similarity 0.85)
- High-Quality Stereo Image Restoration From Double Refraction (CVPR 2021 · similarity 0.85)
- Any-Stereo: Arbitrary Scale Disparity Estimation for Iterative Stereo Matching (AAAI 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.